Estimation of the odds-ratio in an observational study using bandwidth-matching

被引：10

作者：

Bhattacharya, PK ^{[1
]}

Gastwirth, JL

机构：

[1] Univ Calif Davis, Div Stat, Davis, CA 95616 USA

[2] George Washington Univ, Washington, DC 20052 USA

来源：

JOURNAL OF NONPARAMETRIC STATISTICS | 1999年 / 11卷 / 1-3期

基金：

美国国家科学基金会;

关键词：

covariate; binary response; treatment effect; interaction; Mantel-Haenszel estimator;

D O I：

10.1080/10485259908832772

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

In many practical situations, such as incidence of a disease in two groups, a binary response variate Y depends on the effect of one of two treatments as well as a covariate X having different distributions under the two treatments. For this, consider the model: P(Y-i = 1\x) = p(i)(x). P(Y-i = 0\x) = q(i)(x), i = 1,2 in the two treatment groups. If the odds-ratio theta(x) = (p(1)(x)q(2)(x))/(q(1),(x)p(2)(x)) is a constant, then it represents the treatment effect; otherwise, one can only think of a treatment main effect in the presence of a treatment-covariate interaction. A bandwidth-matched version of the Mantel-Haenszel estimator of the odds-ratio is constructed, which is shown to be a consistent estimator of the treatment main effect and normally distributed in large samples.

引用

页码：1 / 12

页数：12